{"id":"https://openalex.org/W4306986475","doi":"https://doi.org/10.1021/acs.jcim.2c01149","title":"Assessment of the Generalization Abilities of Machine-Learning Scoring Functions for Structure-Based Virtual Screening","display_name":"Assessment of the Generalization Abilities of Machine-Learning Scoring Functions for Structure-Based Virtual Screening","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4306986475","doi":"https://doi.org/10.1021/acs.jcim.2c01149","pmid":"https://pubmed.ncbi.nlm.nih.gov/36268980"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c01149","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01149","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040344252","display_name":"Hui Zhu","orcid":"https://orcid.org/0000-0002-4024-374X"},"institutions":[{"id":"https://openalex.org/I4210086405","display_name":"National Institute of Biological Sciences, Beijing","ror":"https://ror.org/00wksha49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210086405"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhu","raw_affiliation_strings":["National Institute of Biological Sciences, 7 Science Park Road, Zhongguancun Life Science Park, Beijing102206, China","Tsinghua Institute of Multidisciplinary Biomedical Research, Tsinghua University, Beijing, China102206, China"],"affiliations":[{"raw_affiliation_string":"National Institute of Biological Sciences, 7 Science Park Road, Zhongguancun Life Science Park, Beijing102206, China","institution_ids":["https://openalex.org/I4210086405"]},{"raw_affiliation_string":"Tsinghua Institute of Multidisciplinary Biomedical Research, Tsinghua University, Beijing, China102206, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044785440","display_name":"Jincai Yang","orcid":"https://orcid.org/0000-0002-0033-0187"},"institutions":[{"id":"https://openalex.org/I4210086405","display_name":"National Institute of Biological Sciences, Beijing","ror":"https://ror.org/00wksha49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210086405"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jincai Yang","raw_affiliation_strings":["National Institute of Biological Sciences, 7 Science Park Road, Zhongguancun Life Science Park, Beijing102206, China"],"affiliations":[{"raw_affiliation_string":"National Institute of Biological Sciences, 7 Science Park Road, Zhongguancun Life Science Park, Beijing102206, China","institution_ids":["https://openalex.org/I4210086405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074665620","display_name":"Niu Huang","orcid":"https://orcid.org/0000-0002-6912-033X"},"institutions":[{"id":"https://openalex.org/I4210086405","display_name":"National Institute of Biological Sciences, Beijing","ror":"https://ror.org/00wksha49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210086405"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Niu Huang","raw_affiliation_strings":["National Institute of Biological Sciences, 7 Science Park Road, Zhongguancun Life Science Park, Beijing102206, China","Tsinghua Institute of Multidisciplinary Biomedical Research, Tsinghua University, Beijing, China102206, China"],"affiliations":[{"raw_affiliation_string":"National Institute of Biological Sciences, 7 Science Park Road, Zhongguancun Life Science Park, Beijing102206, China","institution_ids":["https://openalex.org/I4210086405"]},{"raw_affiliation_string":"Tsinghua Institute of Multidisciplinary Biomedical Research, Tsinghua University, Beijing, China102206, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044785440","https://openalex.org/A5074665620"],"corresponding_institution_ids":["https://openalex.org/I4210086405","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.257,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.9620193,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"62","issue":"22","first_page":"5485","last_page":"5502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sasa","display_name":"Sasa","score":0.7316423654556274},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.703821063041687},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6502718925476074},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5658547878265381},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.552903950214386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4709549844264984},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.469020277261734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46535545587539673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44458407163619995},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.433788925409317},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3613284230232239},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.29818692803382874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2607935667037964},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.258914053440094},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.11422225832939148}],"concepts":[{"id":"https://openalex.org/C2776335000","wikidata":"https://www.wikidata.org/wiki/Q2322484","display_name":"Sasa","level":2,"score":0.7316423654556274},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.703821063041687},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6502718925476074},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5658547878265381},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.552903950214386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4709549844264984},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.469020277261734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46535545587539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44458407163619995},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.433788925409317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3613284230232239},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.29818692803382874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2607935667037964},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.258914053440094},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.11422225832939148},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.2c01149","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01149","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:36268980","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36268980","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3487226201","display_name":null,"funder_award_id":"Z211100003321007","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"},{"id":"https://openalex.org/G414636982","display_name":null,"funder_award_id":"2022-ZZ-012","funder_id":"https://openalex.org/F4320323068","funder_display_name":"Beijing Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7060692123","display_name":null,"funder_award_id":"Z201100005320012","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320323068","display_name":"Beijing Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W1212579592","https://openalex.org/W1950993160","https://openalex.org/W1974324284","https://openalex.org/W1975135696","https://openalex.org/W1985588649","https://openalex.org/W1991139280","https://openalex.org/W1992441011","https://openalex.org/W1993046136","https://openalex.org/W1993285168","https://openalex.org/W1993403967","https://openalex.org/W2000750728","https://openalex.org/W2020372058","https://openalex.org/W2022998385","https://openalex.org/W2023717652","https://openalex.org/W2035292911","https://openalex.org/W2039361751","https://openalex.org/W2041767096","https://openalex.org/W2043014039","https://openalex.org/W2060051385","https://openalex.org/W2074978477","https://openalex.org/W2086679478","https://openalex.org/W2096541451","https://openalex.org/W2097638191","https://openalex.org/W2101234009","https://openalex.org/W2114850508","https://openalex.org/W2118587156","https://openalex.org/W2127073449","https://openalex.org/W2128307445","https://openalex.org/W2128983966","https://openalex.org/W2130195458","https://openalex.org/W2132314731","https://openalex.org/W2132629607","https://openalex.org/W2135621733","https://openalex.org/W2136280642","https://openalex.org/W2138072853","https://openalex.org/W2140345256","https://openalex.org/W2141528038","https://openalex.org/W2147988069","https://openalex.org/W2148512505","https://openalex.org/W2157484293","https://openalex.org/W2162196815","https://openalex.org/W2199426173","https://openalex.org/W2274656763","https://openalex.org/W2295598076","https://openalex.org/W2468923062","https://openalex.org/W2527541313","https://openalex.org/W2550887636","https://openalex.org/W2558999090","https://openalex.org/W2566079294","https://openalex.org/W2575277381","https://openalex.org/W2584797493","https://openalex.org/W2600971009","https://openalex.org/W2607720215","https://openalex.org/W2753976923","https://openalex.org/W2774371249","https://openalex.org/W2781625157","https://openalex.org/W2781821160","https://openalex.org/W2784213390","https://openalex.org/W2792758786","https://openalex.org/W2792951589","https://openalex.org/W2793600274","https://openalex.org/W2810001758","https://openalex.org/W2893435209","https://openalex.org/W2895884529","https://openalex.org/W2902435351","https://openalex.org/W2902812092","https://openalex.org/W2910318997","https://openalex.org/W2911964244","https://openalex.org/W2912171584","https://openalex.org/W2921473648","https://openalex.org/W2935701257","https://openalex.org/W2950346042","https://openalex.org/W2951676304","https://openalex.org/W2955986556","https://openalex.org/W2962862931","https://openalex.org/W2963833291","https://openalex.org/W2963883198","https://openalex.org/W2964244478","https://openalex.org/W2969325194","https://openalex.org/W2974531988","https://openalex.org/W2982145277","https://openalex.org/W2984249386","https://openalex.org/W2999006441","https://openalex.org/W3001282080","https://openalex.org/W3001433048","https://openalex.org/W3002363522","https://openalex.org/W3005776600","https://openalex.org/W3008726875","https://openalex.org/W3016970897","https://openalex.org/W3028815767","https://openalex.org/W3082411326","https://openalex.org/W3095583226","https://openalex.org/W3098189759","https://openalex.org/W3103934428","https://openalex.org/W3135935512","https://openalex.org/W3140330522","https://openalex.org/W3146467503","https://openalex.org/W3167575787","https://openalex.org/W4200139236","https://openalex.org/W4213426032","https://openalex.org/W4220662284","https://openalex.org/W4289518623"],"related_works":["https://openalex.org/W2398796592","https://openalex.org/W4310471119","https://openalex.org/W2280647617","https://openalex.org/W2185678017","https://openalex.org/W2299861993","https://openalex.org/W2190250622","https://openalex.org/W2014342595","https://openalex.org/W2900229032","https://openalex.org/W243156713","https://openalex.org/W4318022805"],"abstract_inverted_index":{"In":[0],"structure-based":[1],"virtual":[2],"screening":[3],"(SBVS),":[4],"it":[5],"is":[6],"critical":[7],"that":[8,91,130],"scoring":[9,42],"functions":[10,43],"capture":[11],"protein-ligand":[12,120],"atomic":[13],"interactions.":[14],"By":[15,122],"focusing":[16],"on":[17,94,101,116,155],"the":[18,36,69,92,139,142,151,162,168,175],"local":[19],"domains":[20],"of":[21,40,68,108,165],"ligand":[22],"binding":[23,114],"pockets,":[24],"a":[25,147],"standardized":[26],"pocket":[27,61],"Pfam-based":[28,62],"clustering":[29],"(Pfam-cluster)":[30],"approach":[31,170],"was":[32],"developed":[33],"to":[34,77,79],"assess":[35],"cross-target":[37],"generalization":[38,85,163],"ability":[39,164],"machine-learning":[41],"(MLSFs).":[44],"Subsequently,":[45],"12":[46],"typical":[47],"MLSFs":[48,98,166],"were":[49,99,131],"evaluated":[50],"using":[51],"random":[52,143],"cross-validation":[53,58,63],"(Random-CV),":[54],"protein":[55],"sequence":[56],"similarity-based":[57],"(Seq-CV),":[59],"and":[60,171],"(Pfam-CV)":[64],"methods.":[65],"Surprisingly,":[66],"all":[67],"tested":[70],"models":[71],"showed":[72],"decreased":[73],"performances":[74],"from":[75],"Random-CV":[76,152],"Seq-CV":[78],"Pfam-CV":[80],"experiments,":[81],"not":[82],"showing":[83],"satisfactory":[84],"capacity.":[86],"Our":[87],"interpretable":[88],"analysis":[89],"suggested":[90],"predictions":[93],"novel":[95],"targets":[96],"by":[97,178],"dependent":[100],"buried":[102,124],"solvent-accessible":[103],"surface":[104],"area":[105],"(SASA)-related":[106],"features":[107,126,176],"complex":[109],"structures,":[110],"with":[111,127,167,174],"greater":[112],"predicted":[113],"affinities":[115],"complexes":[117],"owning":[118],"larger":[119],"interfaces.":[121],"combining":[123],"SASA-related":[125],"target-specific":[128],"patterns":[129],"only":[132],"shared":[133],"among":[134],"structurally":[135],"similar":[136],"compounds":[137],"in":[138,150],"same":[140],"cluster,":[141],"forest":[144],"(RF)-Score":[145],"attained":[146],"good":[148],"performance":[149],"test.":[153],"Based":[154],"these":[156],"findings,":[157],"we":[158],"strongly":[159],"advise":[160],"assessing":[161],"Pfam-cluster":[169],"being":[172],"cautious":[173],"learned":[177],"MLSFs.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}